Fine tune and Serve Faster Whisper Turbo

[@savanthtadepalli3968]

Superb content as usual! You are a God Ronan! Can you please make a video on a multi-agent use case that involves all three modalities and open source models. I would love to pay for such an end-to-end real world use case and learn from you! Please make it production grade.

[@gr8tbigtreehugger]

Many thanks! I am working on transcription, so much appreciated!

[@btaranto]

Very well structured your videos! From beginning to end! Thank you so much!

[@TrelisResearch]

Thanks very much

[@alexandermaessen407]

Dear Ronan, I am following your instructions. Also purchases your ADVANCED Transcriptions scripts. At 11:50 you explain how to use your template and deploy the prod on runpod. Then when I click on my prod and connect to Jupiter Lab, Jupiter Lab opens but I do not see the notebook? I am a complete beginner to those platforms. Which step did I miss?

[@TrelisResearch]

Howdy. Yes, when you connect to Jupyter lab, you need to upload the ipynb notebook. You can either download that from the GitHub repo you bought access to OR you can git clone the repo to your computer and then upload from your computer. BTW, if you bought repo access, you can create an "Issue" within that GitHub repo, to get help/support!

[@alexandermaessen407]

@@TrelisResearch Amazing, thank you dear Ronan. I will do this.

[@jitindoriya2375]

You are amazing Ronan

[@TrelisResearch]

Thanks

[@iasadkamran]

I rarely comment or subscribe. You deserve a lot more than that 🎩🎩

[@TrelisResearch]

Appreciate it

[@uwegenosdude]

Really cool stuff. Thanks a lot. BTW: We tried insanely fast whisper and it worked pretty well and it is really fast.

[@TrelisResearch]

Really nice

[@hgwvandam]

Oh thanks man!, just what I was looking for!

[@sofias-i9v]

Thank you so much! Very helpful 💚

[@stepanda1725]

On 11:53 After connecting to Jupyter Notebook, I don't see Whisper fine-tuning notebook. Where should I get it and how to put it there? I've purchased Lifetime Access, but didn't receive any access details yet.

[@TrelisResearch]

Howdy, you should have received an email from Github AND on your github activity page, you should have access to the advanced-transcription repo - that's where the script is. I'll email you now to ensure you get in

[@alexandermaessen407]

Hello @@TrelisResearch I am having the same issue. I have it in github but I do not know how to connect the runpod pod whith Jupyter. Wenn clickin on connect it just opens an empty notebook.

[@alexandermaessen407]

Hello @stepanda1725 have you found a solution?

[@BhavikSonkusare]

very informative and useful video Please make a video on how to use whisper in real time ASR.

[@TrelisResearch]

Thanks yeah I’ll keep that in mind as an idea.

[@rezatakhshid8928]

@@TrelisResearch +1 on this one.

[@KopikoArepo]

🎉 thanks!!

[@johnkidsman]

It would be perfect if you could have explained the data collator part in more detail! It's difficult to understand how the paddings work internally

[@TrelisResearch]

oooh yeah, it's true, I think I go into it in a bit more detail if you find my other whisper video from 6+ months ago

[@johnkidsman]

@@TrelisResearch Thanks! Big fan of you!

[@thomashuynh6263]

Can you try fine-tuning on the lagre-v3 model and test fine-tuned model works as expected.

[@TrelisResearch]

It's best to keep the channel's videos broad and not too overlapping with existing content.

[@renatox5288]

whisper faster or whisper turbo?

[@TrelisResearch]

I combine both! Whisper turbo is the model and faster whisper is the inference engine